Hugging Face's logo

heromiya
/
segformer-b0-finetuned-segments-sidewalk-2

Image Segmentation
Transformers
TensorBoard
Safetensors
segformer
vision
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
heromiya commited on
Commit
ce514f5
·
verified ·
1 Parent(s): 7d80aea

End of training

Browse files
Files changed (6) hide show
  1. README.md +46 -61
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/Jan20_10-03-13_jupyter-admin01/events.out.tfevents.1737367409.jupyter-admin01.120.4 +3 -0
  5. runs/Jan20_10-08-48_jupyter-admin01/events.out.tfevents.1737367742.jupyter-admin01.120.5 +3 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -17,79 +17,79 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [aaa](https://huggingface.co/aaa) on the segments/sidewalk-semantic dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.8239
21
- - Mean Iou: 0.1931
22
- - Mean Accuracy: 0.2416
23
- - Overall Accuracy: 0.7807
24
  - Accuracy Unlabeled: nan
25
- - Accuracy Flat-road: 0.8160
26
- - Accuracy Flat-sidewalk: 0.9520
27
  - Accuracy Flat-crosswalk: 0.0
28
- - Accuracy Flat-cyclinglane: 0.5612
29
- - Accuracy Flat-parkingdriveway: 0.3419
30
  - Accuracy Flat-railtrack: nan
31
- - Accuracy Flat-curb: 0.1821
32
  - Accuracy Human-person: 0.0
33
  - Accuracy Human-rider: 0.0
34
- - Accuracy Vehicle-car: 0.9302
35
  - Accuracy Vehicle-truck: 0.0
36
- - Accuracy Vehicle-bus: nan
37
- - Accuracy Vehicle-tramtrain: 0.0
38
  - Accuracy Vehicle-motorcycle: 0.0
39
- - Accuracy Vehicle-bicycle: 0.0197
40
  - Accuracy Vehicle-caravan: 0.0
41
  - Accuracy Vehicle-cartrailer: 0.0
42
- - Accuracy Construction-building: 0.8900
43
  - Accuracy Construction-door: 0.0
44
- - Accuracy Construction-wall: 0.0438
45
- - Accuracy Construction-fenceguardrail: 0.0138
46
  - Accuracy Construction-bridge: 0.0
47
  - Accuracy Construction-tunnel: nan
48
  - Accuracy Construction-stairs: 0.0
49
- - Accuracy Object-pole: 0.0029
50
  - Accuracy Object-trafficsign: 0.0
51
  - Accuracy Object-trafficlight: 0.0
52
- - Accuracy Nature-vegetation: 0.9273
53
- - Accuracy Nature-terrain: 0.8713
54
- - Accuracy Sky: 0.9345
55
  - Accuracy Void-ground: 0.0
56
  - Accuracy Void-dynamic: 0.0
57
- - Accuracy Void-static: 0.0029
58
  - Accuracy Void-unclear: 0.0
59
  - Iou Unlabeled: nan
60
- - Iou Flat-road: 0.5978
61
- - Iou Flat-sidewalk: 0.8216
62
  - Iou Flat-crosswalk: 0.0
63
- - Iou Flat-cyclinglane: 0.4869
64
- - Iou Flat-parkingdriveway: 0.2597
65
- - Iou Flat-railtrack: nan
66
- - Iou Flat-curb: 0.1645
67
  - Iou Human-person: 0.0
68
  - Iou Human-rider: 0.0
69
- - Iou Vehicle-car: 0.7282
70
  - Iou Vehicle-truck: 0.0
71
- - Iou Vehicle-bus: nan
72
- - Iou Vehicle-tramtrain: 0.0
73
  - Iou Vehicle-motorcycle: 0.0
74
- - Iou Vehicle-bicycle: 0.0196
75
  - Iou Vehicle-caravan: 0.0
76
  - Iou Vehicle-cartrailer: 0.0
77
- - Iou Construction-building: 0.6103
78
  - Iou Construction-door: 0.0
79
- - Iou Construction-wall: 0.0419
80
- - Iou Construction-fenceguardrail: 0.0138
81
  - Iou Construction-bridge: 0.0
82
  - Iou Construction-tunnel: nan
83
  - Iou Construction-stairs: 0.0
84
- - Iou Object-pole: 0.0028
85
  - Iou Object-trafficsign: 0.0
86
  - Iou Object-trafficlight: 0.0
87
- - Iou Nature-vegetation: 0.7722
88
- - Iou Nature-terrain: 0.6193
89
- - Iou Sky: 0.8442
90
  - Iou Void-ground: 0.0
91
  - Iou Void-dynamic: 0.0
92
- - Iou Void-static: 0.0028
93
  - Iou Void-unclear: 0.0
94
 
95
  ## Model description
@@ -110,8 +110,8 @@ More information needed
110
 
111
  The following hyperparameters were used during training:
112
  - learning_rate: 6e-05
113
- - train_batch_size: 2
114
- - eval_batch_size: 2
115
  - seed: 42
116
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
117
  - lr_scheduler_type: linear
@@ -121,26 +121,11 @@ The following hyperparameters were used during training:
121
 
122
  | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabeled | Accuracy Flat-road | Accuracy Flat-sidewalk | Accuracy Flat-crosswalk | Accuracy Flat-cyclinglane | Accuracy Flat-parkingdriveway | Accuracy Flat-railtrack | Accuracy Flat-curb | Accuracy Human-person | Accuracy Human-rider | Accuracy Vehicle-car | Accuracy Vehicle-truck | Accuracy Vehicle-bus | Accuracy Vehicle-tramtrain | Accuracy Vehicle-motorcycle | Accuracy Vehicle-bicycle | Accuracy Vehicle-caravan | Accuracy Vehicle-cartrailer | Accuracy Construction-building | Accuracy Construction-door | Accuracy Construction-wall | Accuracy Construction-fenceguardrail | Accuracy Construction-bridge | Accuracy Construction-tunnel | Accuracy Construction-stairs | Accuracy Object-pole | Accuracy Object-trafficsign | Accuracy Object-trafficlight | Accuracy Nature-vegetation | Accuracy Nature-terrain | Accuracy Sky | Accuracy Void-ground | Accuracy Void-dynamic | Accuracy Void-static | Accuracy Void-unclear | Iou Unlabeled | Iou Flat-road | Iou Flat-sidewalk | Iou Flat-crosswalk | Iou Flat-cyclinglane | Iou Flat-parkingdriveway | Iou Flat-railtrack | Iou Flat-curb | Iou Human-person | Iou Human-rider | Iou Vehicle-car | Iou Vehicle-truck | Iou Vehicle-bus | Iou Vehicle-tramtrain | Iou Vehicle-motorcycle | Iou Vehicle-bicycle | Iou Vehicle-caravan | Iou Vehicle-cartrailer | Iou Construction-building | Iou Construction-door | Iou Construction-wall | Iou Construction-fenceguardrail | Iou Construction-bridge | Iou Construction-tunnel | Iou Construction-stairs | Iou Object-pole | Iou Object-trafficsign | Iou Object-trafficlight | Iou Nature-vegetation | Iou Nature-terrain | Iou Sky | Iou Void-ground | Iou Void-dynamic | Iou Void-static | Iou Void-unclear |
123
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:------------------:|:----------------------:|:-----------------------:|:-------------------------:|:-----------------------------:|:-----------------------:|:------------------:|:---------------------:|:--------------------:|:--------------------:|:----------------------:|:--------------------:|:--------------------------:|:---------------------------:|:------------------------:|:------------------------:|:---------------------------:|:------------------------------:|:--------------------------:|:--------------------------:|:------------------------------------:|:----------------------------:|:----------------------------:|:----------------------------:|:--------------------:|:---------------------------:|:----------------------------:|:--------------------------:|:-----------------------:|:------------:|:--------------------:|:---------------------:|:--------------------:|:---------------------:|:-------------:|:-------------:|:-----------------:|:------------------:|:--------------------:|:------------------------:|:------------------:|:-------------:|:----------------:|:---------------:|:---------------:|:-----------------:|:---------------:|:---------------------:|:----------------------:|:-------------------:|:-------------------:|:----------------------:|:-------------------------:|:---------------------:|:---------------------:|:-------------------------------:|:-----------------------:|:-----------------------:|:-----------------------:|:---------------:|:----------------------:|:-----------------------:|:---------------------:|:------------------:|:-------:|:---------------:|:----------------:|:---------------:|:----------------:|
124
- | 0.8103 | 0.05 | 20 | 0.9746 | 0.1718 | 0.2202 | 0.7576 | nan | 0.8477 | 0.9412 | 0.0 | 0.3997 | 0.1450 | nan | 0.0275 | 0.0 | 0.0 | 0.9028 | 0.0 | nan | 0.0 | 0.0 | 0.0100 | 0.0 | 0.0 | 0.8502 | 0.0 | 0.0044 | 0.0010 | 0.0 | nan | 0.0 | 0.0001 | 0.0 | 0.0 | 0.9360 | 0.8241 | 0.9366 | 0.0 | 0.0 | 0.0000 | 0.0 | nan | 0.5454 | 0.8072 | 0.0 | 0.3789 | 0.1296 | nan | 0.0267 | 0.0 | 0.0 | 0.7183 | 0.0 | nan | 0.0 | 0.0 | 0.0100 | 0.0 | 0.0 | 0.5732 | 0.0 | 0.0043 | 0.0010 | 0.0 | nan | 0.0 | 0.0001 | 0.0 | 0.0 | 0.7415 | 0.5942 | 0.7965 | 0.0 | 0.0 | 0.0000 | 0.0 |
125
- | 1.7413 | 0.1 | 40 | 0.9511 | 0.1781 | 0.2282 | 0.7573 | nan | 0.8166 | 0.9130 | 0.0 | 0.6194 | 0.2478 | nan | 0.0035 | 0.0 | 0.0 | 0.8966 | 0.0 | nan | 0.0 | 0.0 | 0.0146 | 0.0 | 0.0 | 0.8735 | 0.0 | 0.0309 | 0.0030 | 0.0 | nan | 0.0 | 0.0000 | 0.0 | 0.0 | 0.9278 | 0.8164 | 0.9099 | 0.0 | 0.0 | 0.0015 | 0.0 | nan | 0.5149 | 0.8077 | 0.0 | 0.4175 | 0.1995 | nan | 0.0034 | 0.0 | 0.0 | 0.7325 | 0.0 | nan | 0.0 | 0.0 | 0.0146 | 0.0 | 0.0 | 0.5807 | 0.0 | 0.0303 | 0.0030 | 0.0 | nan | 0.0 | 0.0000 | 0.0 | 0.0 | 0.7787 | 0.6302 | 0.8076 | 0.0 | 0.0 | 0.0015 | 0.0 |
126
- | 0.692 | 0.15 | 60 | 0.9307 | 0.1851 | 0.2341 | 0.7695 | nan | 0.8016 | 0.9491 | 0.0 | 0.5280 | 0.3609 | nan | 0.0535 | 0.0 | 0.0 | 0.9267 | 0.0 | nan | 0.0 | 0.0 | 0.0271 | 0.0 | 0.0 | 0.8734 | 0.0 | 0.0405 | 0.0075 | 0.0 | nan | 0.0 | 0.0026 | 0.0 | 0.0 | 0.9147 | 0.8389 | 0.9332 | 0.0 | 0.0 | 0.0007 | 0.0 | nan | 0.5891 | 0.8055 | 0.0 | 0.4621 | 0.2304 | nan | 0.0518 | 0.0 | 0.0 | 0.7174 | 0.0 | nan | 0.0 | 0.0 | 0.0269 | 0.0 | 0.0 | 0.5887 | 0.0 | 0.0389 | 0.0075 | 0.0 | nan | 0.0 | 0.0026 | 0.0 | 0.0 | 0.7713 | 0.6311 | 0.8129 | 0.0 | 0.0 | 0.0007 | 0.0 |
127
- | 0.7596 | 0.2 | 80 | 0.9096 | 0.1793 | 0.2257 | 0.7644 | nan | 0.7815 | 0.9509 | 0.0 | 0.5495 | 0.1955 | nan | 0.0374 | 0.0 | 0.0 | 0.9207 | 0.0 | nan | 0.0 | 0.0 | 0.0102 | 0.0 | 0.0 | 0.8699 | 0.0 | 0.0341 | 0.0049 | 0.0 | nan | 0.0 | 0.0006 | 0.0 | 0.0 | 0.9466 | 0.7815 | 0.9138 | 0.0 | 0.0 | 0.0010 | 0.0 | nan | 0.5539 | 0.7985 | 0.0 | 0.4484 | 0.1637 | nan | 0.0356 | 0.0 | 0.0 | 0.7185 | 0.0 | nan | 0.0 | 0.0 | 0.0101 | 0.0 | 0.0 | 0.5927 | 0.0 | 0.0333 | 0.0049 | 0.0 | nan | 0.0 | 0.0006 | 0.0 | 0.0 | 0.7622 | 0.6136 | 0.8211 | 0.0 | 0.0 | 0.0010 | 0.0 |
128
- | 2.488 | 0.25 | 100 | 0.9044 | 0.1835 | 0.2322 | 0.7664 | nan | 0.7793 | 0.9515 | 0.0 | 0.5437 | 0.2497 | nan | 0.0512 | 0.0 | 0.0 | 0.9240 | 0.0 | nan | 0.0 | 0.0 | 0.0722 | 0.0 | 0.0 | 0.8669 | 0.0 | 0.0363 | 0.0049 | 0.0 | nan | 0.0 | 0.0009 | 0.0 | 0.0 | 0.9261 | 0.8535 | 0.9367 | 0.0 | 0.0 | 0.0012 | 0.0 | nan | 0.5586 | 0.7977 | 0.0 | 0.4503 | 0.1989 | nan | 0.0484 | 0.0 | 0.0 | 0.7180 | 0.0 | nan | 0.0 | 0.0 | 0.0674 | 0.0 | 0.0 | 0.5927 | 0.0 | 0.0348 | 0.0049 | 0.0 | nan | 0.0 | 0.0009 | 0.0 | 0.0 | 0.7728 | 0.6322 | 0.8112 | 0.0 | 0.0 | 0.0012 | 0.0 |
129
- | 1.6014 | 0.3 | 120 | 0.8943 | 0.1874 | 0.2321 | 0.7711 | nan | 0.8302 | 0.9494 | 0.0 | 0.5641 | 0.2765 | nan | 0.0432 | 0.0 | 0.0 | 0.8936 | 0.0 | nan | 0.0 | 0.0 | 0.1394 | 0.0 | 0.0 | 0.8763 | 0.0 | 0.0239 | 0.0041 | 0.0 | nan | 0.0 | 0.0009 | 0.0 | 0.0 | 0.9514 | 0.7223 | 0.9152 | 0.0 | 0.0 | 0.0050 | 0.0 | nan | 0.5715 | 0.8205 | 0.0 | 0.4636 | 0.2248 | nan | 0.0418 | 0.0 | 0.0 | 0.7530 | 0.0 | nan | 0.0 | 0.0 | 0.1357 | 0.0 | 0.0 | 0.5966 | 0.0 | 0.0226 | 0.0041 | 0.0 | nan | 0.0 | 0.0009 | 0.0 | 0.0 | 0.7472 | 0.5855 | 0.8355 | 0.0 | 0.0 | 0.0049 | 0.0 |
130
- | 0.8147 | 0.35 | 140 | 0.8695 | 0.1846 | 0.2319 | 0.7745 | nan | 0.8367 | 0.9532 | 0.0 | 0.5543 | 0.2277 | nan | 0.0740 | 0.0 | 0.0 | 0.9383 | 0.0 | nan | 0.0 | 0.0 | 0.0167 | 0.0 | 0.0 | 0.8803 | 0.0 | 0.0103 | 0.0131 | 0.0 | nan | 0.0 | 0.0004 | 0.0 | 0.0 | 0.9296 | 0.8342 | 0.9152 | 0.0 | 0.0 | 0.0052 | 0.0 | nan | 0.5823 | 0.8141 | 0.0 | 0.4597 | 0.1945 | nan | 0.0710 | 0.0 | 0.0 | 0.7107 | 0.0 | nan | 0.0 | 0.0 | 0.0166 | 0.0 | 0.0 | 0.5990 | 0.0 | 0.0101 | 0.0131 | 0.0 | nan | 0.0 | 0.0004 | 0.0 | 0.0 | 0.7821 | 0.6278 | 0.8370 | 0.0 | 0.0 | 0.0051 | 0.0 |
131
- | 1.4018 | 0.4 | 160 | 0.8790 | 0.1844 | 0.2351 | 0.7723 | nan | 0.8652 | 0.9375 | 0.0 | 0.5785 | 0.2377 | nan | 0.0621 | 0.0 | 0.0 | 0.9270 | 0.0 | nan | 0.0 | 0.0 | 0.0396 | 0.0 | 0.0 | 0.8421 | 0.0 | 0.0235 | 0.0171 | 0.0 | nan | 0.0 | 0.0011 | 0.0 | 0.0 | 0.9285 | 0.8759 | 0.9466 | 0.0 | 0.0 | 0.0067 | 0.0 | nan | 0.5660 | 0.8249 | 0.0 | 0.4696 | 0.2068 | nan | 0.0586 | 0.0 | 0.0 | 0.7163 | 0.0 | nan | 0.0 | 0.0 | 0.0388 | 0.0 | 0.0 | 0.5986 | 0.0 | 0.0228 | 0.0170 | 0.0 | nan | 0.0 | 0.0011 | 0.0 | 0.0 | 0.7677 | 0.6210 | 0.8002 | 0.0 | 0.0 | 0.0066 | 0.0 |
132
- | 0.7772 | 0.45 | 180 | 0.8748 | 0.1832 | 0.2319 | 0.7717 | nan | 0.8387 | 0.9436 | 0.0 | 0.4977 | 0.2897 | nan | 0.0829 | 0.0 | 0.0 | 0.9349 | 0.0 | nan | 0.0 | 0.0 | 0.0030 | 0.0 | 0.0 | 0.8920 | 0.0 | 0.0127 | 0.0049 | 0.0 | nan | 0.0 | 0.0007 | 0.0 | 0.0 | 0.9250 | 0.8519 | 0.9101 | 0.0 | 0.0 | 0.0016 | 0.0 | nan | 0.5636 | 0.8240 | 0.0 | 0.4565 | 0.2318 | nan | 0.0784 | 0.0 | 0.0 | 0.7010 | 0.0 | nan | 0.0 | 0.0 | 0.0030 | 0.0 | 0.0 | 0.5801 | 0.0 | 0.0123 | 0.0049 | 0.0 | nan | 0.0 | 0.0007 | 0.0 | 0.0 | 0.7830 | 0.6197 | 0.8200 | 0.0 | 0.0 | 0.0016 | 0.0 |
133
- | 1.4262 | 0.5 | 200 | 0.8587 | 0.1857 | 0.2306 | 0.7754 | nan | 0.8581 | 0.9496 | 0.0 | 0.5187 | 0.2731 | nan | 0.0659 | 0.0 | 0.0 | 0.9169 | 0.0 | nan | 0.0 | 0.0 | 0.0155 | 0.0 | 0.0 | 0.9009 | 0.0 | 0.0225 | 0.0153 | 0.0 | nan | 0.0 | 0.0003 | 0.0 | 0.0 | 0.9412 | 0.7604 | 0.9073 | 0.0 | 0.0 | 0.0025 | 0.0 | nan | 0.5714 | 0.8260 | 0.0 | 0.4711 | 0.2214 | nan | 0.0632 | 0.0 | 0.0 | 0.7344 | 0.0 | nan | 0.0 | 0.0 | 0.0154 | 0.0 | 0.0 | 0.5985 | 0.0 | 0.0218 | 0.0153 | 0.0 | nan | 0.0 | 0.0003 | 0.0 | 0.0 | 0.7744 | 0.6071 | 0.8332 | 0.0 | 0.0 | 0.0025 | 0.0 |
134
- | 1.2186 | 0.55 | 220 | 0.8649 | 0.1848 | 0.2319 | 0.7731 | nan | 0.8396 | 0.9627 | 0.0 | 0.5125 | 0.2021 | nan | 0.0682 | 0.0 | 0.0 | 0.9387 | 0.0 | nan | 0.0 | 0.0 | 0.0188 | 0.0 | 0.0 | 0.8839 | 0.0 | 0.0658 | 0.0186 | 0.0 | nan | 0.0 | 0.0005 | 0.0 | 0.0 | 0.9003 | 0.8545 | 0.9182 | 0.0 | 0.0 | 0.0031 | 0.0 | nan | 0.5779 | 0.8065 | 0.0 | 0.4707 | 0.1771 | nan | 0.0648 | 0.0 | 0.0 | 0.7060 | 0.0 | nan | 0.0 | 0.0 | 0.0186 | 0.0 | 0.0 | 0.6145 | 0.0 | 0.0629 | 0.0185 | 0.0 | nan | 0.0 | 0.0005 | 0.0 | 0.0 | 0.7748 | 0.6009 | 0.8328 | 0.0 | 0.0 | 0.0030 | 0.0 |
135
- | 0.6278 | 0.6 | 240 | 0.8479 | 0.1904 | 0.2391 | 0.7799 | nan | 0.8594 | 0.9419 | 0.0 | 0.5438 | 0.3264 | nan | 0.1602 | 0.0 | 0.0 | 0.9272 | 0.0 | nan | 0.0 | 0.0 | 0.0155 | 0.0 | 0.0 | 0.8946 | 0.0 | 0.0303 | 0.0120 | 0.0 | nan | 0.0 | 0.0010 | 0.0 | 0.0 | 0.9322 | 0.8333 | 0.9331 | 0.0 | 0.0 | 0.0020 | 0.0 | nan | 0.5977 | 0.8311 | 0.0 | 0.4772 | 0.2475 | nan | 0.1469 | 0.0 | 0.0 | 0.7188 | 0.0 | nan | 0.0 | 0.0 | 0.0154 | 0.0 | 0.0 | 0.5999 | 0.0 | 0.0291 | 0.0120 | 0.0 | nan | 0.0 | 0.0010 | 0.0 | 0.0 | 0.7745 | 0.6266 | 0.8229 | 0.0 | 0.0 | 0.0020 | 0.0 |
136
- | 1.0079 | 0.65 | 260 | 0.8485 | 0.1886 | 0.2343 | 0.7805 | nan | 0.8640 | 0.9579 | 0.0 | 0.5106 | 0.2632 | nan | 0.1124 | 0.0 | 0.0 | 0.9376 | 0.0 | nan | 0.0 | 0.0 | 0.0096 | 0.0 | 0.0 | 0.8885 | 0.0 | 0.0329 | 0.0136 | 0.0 | nan | 0.0 | 0.0004 | 0.0 | 0.0 | 0.9343 | 0.8127 | 0.9223 | 0.0 | 0.0 | 0.0019 | 0.0 | nan | 0.5987 | 0.8215 | 0.0 | 0.4701 | 0.2216 | nan | 0.1067 | 0.0 | 0.0 | 0.7123 | 0.0 | nan | 0.0 | 0.0 | 0.0096 | 0.0 | 0.0 | 0.6092 | 0.0 | 0.0320 | 0.0135 | 0.0 | nan | 0.0 | 0.0004 | 0.0 | 0.0 | 0.7770 | 0.6336 | 0.8394 | 0.0 | 0.0 | 0.0019 | 0.0 |
137
- | 2.0554 | 0.7 | 280 | 0.8510 | 0.1881 | 0.2370 | 0.7769 | nan | 0.8456 | 0.9568 | 0.0 | 0.5419 | 0.2858 | nan | 0.0996 | 0.0 | 0.0 | 0.9369 | 0.0 | nan | 0.0 | 0.0 | 0.0160 | 0.0 | 0.0 | 0.9031 | 0.0 | 0.0570 | 0.0106 | 0.0 | nan | 0.0 | 0.0008 | 0.0 | 0.0 | 0.8854 | 0.8785 | 0.9279 | 0.0 | 0.0 | 0.0022 | 0.0 | nan | 0.5974 | 0.8192 | 0.0 | 0.4807 | 0.2335 | nan | 0.0945 | 0.0 | 0.0 | 0.7197 | 0.0 | nan | 0.0 | 0.0 | 0.0159 | 0.0 | 0.0 | 0.6075 | 0.0 | 0.0537 | 0.0106 | 0.0 | nan | 0.0 | 0.0008 | 0.0 | 0.0 | 0.7678 | 0.5841 | 0.8437 | 0.0 | 0.0 | 0.0022 | 0.0 |
138
- | 1.0441 | 0.75 | 300 | 0.8363 | 0.1908 | 0.2393 | 0.7800 | nan | 0.8349 | 0.9499 | 0.0 | 0.5363 | 0.3461 | nan | 0.1354 | 0.0 | 0.0 | 0.9348 | 0.0 | nan | 0.0 | 0.0 | 0.0046 | 0.0 | 0.0 | 0.8976 | 0.0 | 0.0593 | 0.0084 | 0.0 | nan | 0.0 | 0.0008 | 0.0 | 0.0 | 0.9234 | 0.8505 | 0.9344 | 0.0 | 0.0 | 0.0027 | 0.0 | nan | 0.5895 | 0.8290 | 0.0 | 0.4715 | 0.2565 | nan | 0.1260 | 0.0 | 0.0 | 0.7175 | 0.0 | nan | 0.0 | 0.0 | 0.0046 | 0.0 | 0.0 | 0.6058 | 0.0 | 0.0560 | 0.0084 | 0.0 | nan | 0.0 | 0.0008 | 0.0 | 0.0 | 0.7791 | 0.6295 | 0.8368 | 0.0 | 0.0 | 0.0026 | 0.0 |
139
- | 1.061 | 0.8 | 320 | 0.8356 | 0.1911 | 0.2393 | 0.7802 | nan | 0.8391 | 0.9530 | 0.0 | 0.5333 | 0.3409 | nan | 0.1336 | 0.0 | 0.0 | 0.9361 | 0.0 | nan | 0.0 | 0.0 | 0.0043 | 0.0 | 0.0 | 0.8862 | 0.0 | 0.0675 | 0.0068 | 0.0 | nan | 0.0 | 0.0010 | 0.0 | 0.0 | 0.9212 | 0.8563 | 0.9368 | 0.0 | 0.0 | 0.0018 | 0.0 | nan | 0.5936 | 0.8228 | 0.0 | 0.4752 | 0.2582 | nan | 0.1235 | 0.0 | 0.0 | 0.7149 | 0.0 | nan | 0.0 | 0.0 | 0.0043 | 0.0 | 0.0 | 0.6148 | 0.0 | 0.0642 | 0.0068 | 0.0 | nan | 0.0 | 0.0010 | 0.0 | 0.0 | 0.7748 | 0.6278 | 0.8420 | 0.0 | 0.0 | 0.0017 | 0.0 |
140
- | 0.6905 | 0.85 | 340 | 0.8301 | 0.1933 | 0.2408 | 0.7811 | nan | 0.8348 | 0.9523 | 0.0 | 0.5462 | 0.3288 | nan | 0.1606 | 0.0 | 0.0 | 0.9262 | 0.0 | nan | 0.0 | 0.0 | 0.0205 | 0.0 | 0.0 | 0.8805 | 0.0 | 0.0731 | 0.0136 | 0.0 | nan | 0.0 | 0.0022 | 0.0 | 0.0 | 0.9316 | 0.8555 | 0.9364 | 0.0 | 0.0 | 0.0033 | 0.0 | nan | 0.5929 | 0.8226 | 0.0 | 0.4762 | 0.2557 | nan | 0.1449 | 0.0 | 0.0 | 0.7318 | 0.0 | nan | 0.0 | 0.0 | 0.0204 | 0.0 | 0.0 | 0.6170 | 0.0 | 0.0697 | 0.0136 | 0.0 | nan | 0.0 | 0.0022 | 0.0 | 0.0 | 0.7711 | 0.6300 | 0.8408 | 0.0 | 0.0 | 0.0033 | 0.0 |
141
- | 0.7337 | 0.9 | 360 | 0.8207 | 0.1933 | 0.2402 | 0.7816 | nan | 0.8343 | 0.9555 | 0.0 | 0.5336 | 0.3394 | nan | 0.1672 | 0.0 | 0.0 | 0.9309 | 0.0 | nan | 0.0 | 0.0 | 0.0234 | 0.0 | 0.0 | 0.8946 | 0.0 | 0.0376 | 0.0101 | 0.0 | nan | 0.0 | 0.0015 | 0.0 | 0.0 | 0.9243 | 0.8546 | 0.9349 | 0.0 | 0.0 | 0.0036 | 0.0 | nan | 0.5978 | 0.8180 | 0.0 | 0.4807 | 0.2607 | nan | 0.1526 | 0.0 | 0.0 | 0.7310 | 0.0 | nan | 0.0 | 0.0 | 0.0232 | 0.0 | 0.0 | 0.6100 | 0.0 | 0.0360 | 0.0101 | 0.0 | nan | 0.0 | 0.0015 | 0.0 | 0.0 | 0.7829 | 0.6405 | 0.8452 | 0.0 | 0.0 | 0.0036 | 0.0 |
142
- | 0.8342 | 0.95 | 380 | 0.8296 | 0.1917 | 0.2379 | 0.7787 | nan | 0.8022 | 0.9614 | 0.0 | 0.5471 | 0.2965 | nan | 0.1562 | 0.0 | 0.0 | 0.9249 | 0.0 | nan | 0.0 | 0.0 | 0.0225 | 0.0 | 0.0 | 0.8876 | 0.0 | 0.0379 | 0.0155 | 0.0 | nan | 0.0 | 0.0015 | 0.0 | 0.0 | 0.9284 | 0.8581 | 0.9326 | 0.0 | 0.0 | 0.0039 | 0.0 | nan | 0.6014 | 0.8056 | 0.0 | 0.4835 | 0.2355 | nan | 0.1435 | 0.0 | 0.0 | 0.7366 | 0.0 | nan | 0.0 | 0.0 | 0.0224 | 0.0 | 0.0 | 0.6104 | 0.0 | 0.0364 | 0.0155 | 0.0 | nan | 0.0 | 0.0015 | 0.0 | 0.0 | 0.7727 | 0.6288 | 0.8444 | 0.0 | 0.0 | 0.0038 | 0.0 |
143
- | 0.7096 | 1.0 | 400 | 0.8239 | 0.1931 | 0.2416 | 0.7807 | nan | 0.8160 | 0.9520 | 0.0 | 0.5612 | 0.3419 | nan | 0.1821 | 0.0 | 0.0 | 0.9302 | 0.0 | nan | 0.0 | 0.0 | 0.0197 | 0.0 | 0.0 | 0.8900 | 0.0 | 0.0438 | 0.0138 | 0.0 | nan | 0.0 | 0.0029 | 0.0 | 0.0 | 0.9273 | 0.8713 | 0.9345 | 0.0 | 0.0 | 0.0029 | 0.0 | nan | 0.5978 | 0.8216 | 0.0 | 0.4869 | 0.2597 | nan | 0.1645 | 0.0 | 0.0 | 0.7282 | 0.0 | nan | 0.0 | 0.0 | 0.0196 | 0.0 | 0.0 | 0.6103 | 0.0 | 0.0419 | 0.0138 | 0.0 | nan | 0.0 | 0.0028 | 0.0 | 0.0 | 0.7722 | 0.6193 | 0.8442 | 0.0 | 0.0 | 0.0028 | 0.0 |
144
 
145
 
146
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [aaa](https://huggingface.co/aaa) on the segments/sidewalk-semantic dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 2.4704
21
+ - Mean Iou: 0.1228
22
+ - Mean Accuracy: 0.1842
23
+ - Overall Accuracy: 0.6771
24
  - Accuracy Unlabeled: nan
25
+ - Accuracy Flat-road: 0.8619
26
+ - Accuracy Flat-sidewalk: 0.8589
27
  - Accuracy Flat-crosswalk: 0.0
28
+ - Accuracy Flat-cyclinglane: 0.0530
29
+ - Accuracy Flat-parkingdriveway: 0.0006
30
  - Accuracy Flat-railtrack: nan
31
+ - Accuracy Flat-curb: 0.0
32
  - Accuracy Human-person: 0.0
33
  - Accuracy Human-rider: 0.0
34
+ - Accuracy Vehicle-car: 0.8886
35
  - Accuracy Vehicle-truck: 0.0
36
+ - Accuracy Vehicle-bus: 0.0
37
+ - Accuracy Vehicle-tramtrain: nan
38
  - Accuracy Vehicle-motorcycle: 0.0
39
+ - Accuracy Vehicle-bicycle: 0.0
40
  - Accuracy Vehicle-caravan: 0.0
41
  - Accuracy Vehicle-cartrailer: 0.0
42
+ - Accuracy Construction-building: 0.6177
43
  - Accuracy Construction-door: 0.0
44
+ - Accuracy Construction-wall: 0.0
45
+ - Accuracy Construction-fenceguardrail: 0.0
46
  - Accuracy Construction-bridge: 0.0
47
  - Accuracy Construction-tunnel: nan
48
  - Accuracy Construction-stairs: 0.0
49
+ - Accuracy Object-pole: 0.0
50
  - Accuracy Object-trafficsign: 0.0
51
  - Accuracy Object-trafficlight: 0.0
52
+ - Accuracy Nature-vegetation: 0.9365
53
+ - Accuracy Nature-terrain: 0.5350
54
+ - Accuracy Sky: 0.9510
55
  - Accuracy Void-ground: 0.0
56
  - Accuracy Void-dynamic: 0.0
57
+ - Accuracy Void-static: 0.0074
58
  - Accuracy Void-unclear: 0.0
59
  - Iou Unlabeled: nan
60
+ - Iou Flat-road: 0.4368
61
+ - Iou Flat-sidewalk: 0.7208
62
  - Iou Flat-crosswalk: 0.0
63
+ - Iou Flat-cyclinglane: 0.0505
64
+ - Iou Flat-parkingdriveway: 0.0005
65
+ - Iou Flat-railtrack: 0.0
66
+ - Iou Flat-curb: 0.0
67
  - Iou Human-person: 0.0
68
  - Iou Human-rider: 0.0
69
+ - Iou Vehicle-car: 0.5175
70
  - Iou Vehicle-truck: 0.0
71
+ - Iou Vehicle-bus: 0.0
72
+ - Iou Vehicle-tramtrain: nan
73
  - Iou Vehicle-motorcycle: 0.0
74
+ - Iou Vehicle-bicycle: 0.0
75
  - Iou Vehicle-caravan: 0.0
76
  - Iou Vehicle-cartrailer: 0.0
77
+ - Iou Construction-building: 0.5053
78
  - Iou Construction-door: 0.0
79
+ - Iou Construction-wall: 0.0
80
+ - Iou Construction-fenceguardrail: 0.0
81
  - Iou Construction-bridge: 0.0
82
  - Iou Construction-tunnel: nan
83
  - Iou Construction-stairs: 0.0
84
+ - Iou Object-pole: 0.0
85
  - Iou Object-trafficsign: 0.0
86
  - Iou Object-trafficlight: 0.0
87
+ - Iou Nature-vegetation: 0.6868
88
+ - Iou Nature-terrain: 0.3948
89
+ - Iou Sky: 0.6104
90
  - Iou Void-ground: 0.0
91
  - Iou Void-dynamic: 0.0
92
+ - Iou Void-static: 0.0073
93
  - Iou Void-unclear: 0.0
94
 
95
  ## Model description
 
110
 
111
  The following hyperparameters were used during training:
112
  - learning_rate: 6e-05
113
+ - train_batch_size: 8
114
+ - eval_batch_size: 8
115
  - seed: 42
116
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
117
  - lr_scheduler_type: linear
 
121
 
122
  | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabeled | Accuracy Flat-road | Accuracy Flat-sidewalk | Accuracy Flat-crosswalk | Accuracy Flat-cyclinglane | Accuracy Flat-parkingdriveway | Accuracy Flat-railtrack | Accuracy Flat-curb | Accuracy Human-person | Accuracy Human-rider | Accuracy Vehicle-car | Accuracy Vehicle-truck | Accuracy Vehicle-bus | Accuracy Vehicle-tramtrain | Accuracy Vehicle-motorcycle | Accuracy Vehicle-bicycle | Accuracy Vehicle-caravan | Accuracy Vehicle-cartrailer | Accuracy Construction-building | Accuracy Construction-door | Accuracy Construction-wall | Accuracy Construction-fenceguardrail | Accuracy Construction-bridge | Accuracy Construction-tunnel | Accuracy Construction-stairs | Accuracy Object-pole | Accuracy Object-trafficsign | Accuracy Object-trafficlight | Accuracy Nature-vegetation | Accuracy Nature-terrain | Accuracy Sky | Accuracy Void-ground | Accuracy Void-dynamic | Accuracy Void-static | Accuracy Void-unclear | Iou Unlabeled | Iou Flat-road | Iou Flat-sidewalk | Iou Flat-crosswalk | Iou Flat-cyclinglane | Iou Flat-parkingdriveway | Iou Flat-railtrack | Iou Flat-curb | Iou Human-person | Iou Human-rider | Iou Vehicle-car | Iou Vehicle-truck | Iou Vehicle-bus | Iou Vehicle-tramtrain | Iou Vehicle-motorcycle | Iou Vehicle-bicycle | Iou Vehicle-caravan | Iou Vehicle-cartrailer | Iou Construction-building | Iou Construction-door | Iou Construction-wall | Iou Construction-fenceguardrail | Iou Construction-bridge | Iou Construction-tunnel | Iou Construction-stairs | Iou Object-pole | Iou Object-trafficsign | Iou Object-trafficlight | Iou Nature-vegetation | Iou Nature-terrain | Iou Sky | Iou Void-ground | Iou Void-dynamic | Iou Void-static | Iou Void-unclear |
123
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:------------------:|:----------------------:|:-----------------------:|:-------------------------:|:-----------------------------:|:-----------------------:|:------------------:|:---------------------:|:--------------------:|:--------------------:|:----------------------:|:--------------------:|:--------------------------:|:---------------------------:|:------------------------:|:------------------------:|:---------------------------:|:------------------------------:|:--------------------------:|:--------------------------:|:------------------------------------:|:----------------------------:|:----------------------------:|:----------------------------:|:--------------------:|:---------------------------:|:----------------------------:|:--------------------------:|:-----------------------:|:------------:|:--------------------:|:---------------------:|:--------------------:|:---------------------:|:-------------:|:-------------:|:-----------------:|:------------------:|:--------------------:|:------------------------:|:------------------:|:-------------:|:----------------:|:---------------:|:---------------:|:-----------------:|:---------------:|:---------------------:|:----------------------:|:-------------------:|:-------------------:|:----------------------:|:-------------------------:|:---------------------:|:---------------------:|:-------------------------------:|:-----------------------:|:-----------------------:|:-----------------------:|:---------------:|:----------------------:|:-----------------------:|:---------------------:|:------------------:|:-------:|:---------------:|:----------------:|:---------------:|:----------------:|
124
+ | 3.0949 | 0.2 | 20 | 3.0458 | 0.0819 | 0.1460 | 0.5398 | nan | 0.7787 | 0.7924 | 0.0044 | 0.1968 | 0.0005 | nan | 0.0002 | 0.0438 | 0.0096 | 0.8797 | 0.0059 | 0.0 | nan | 0.0130 | 0.0 | 0.0 | 0.0 | 0.0409 | 0.0 | 0.0023 | 0.0 | 0.0004 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.6323 | 0.2713 | 0.7608 | 0.0000 | 0.0154 | 0.0043 | 0.0720 | 0.0 | 0.4417 | 0.6871 | 0.0038 | 0.1179 | 0.0005 | 0.0 | 0.0002 | 0.0246 | 0.0004 | 0.3778 | 0.0036 | 0.0 | 0.0 | 0.0000 | 0.0 | 0.0 | 0.0 | 0.0401 | 0.0 | 0.0023 | 0.0 | 0.0000 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.5177 | 0.2196 | 0.4219 | 0.0000 | 0.0011 | 0.0042 | 0.0001 |
125
+ | 2.9043 | 0.4 | 40 | 2.7801 | 0.1036 | 0.1809 | 0.6489 | nan | 0.8303 | 0.8567 | 0.0000 | 0.1591 | 0.0005 | nan | 0.0001 | 0.0036 | 0.0 | 0.9453 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.3779 | 0.0 | 0.0003 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.8374 | 0.6238 | 0.9717 | 0.0 | 0.0000 | 0.0014 | 0.0 | 0.0 | 0.4619 | 0.7132 | 0.0000 | 0.1384 | 0.0005 | 0.0 | 0.0001 | 0.0033 | 0.0 | 0.3443 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.3474 | 0.0 | 0.0003 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.6680 | 0.4432 | 0.5029 | 0.0 | 0.0000 | 0.0014 | 0.0 |
126
+ | 2.7418 | 0.6 | 60 | 2.5939 | 0.1131 | 0.1800 | 0.6631 | nan | 0.8577 | 0.8508 | 0.0 | 0.0594 | 0.0004 | nan | 0.0000 | 0.0002 | 0.0 | 0.9340 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.5521 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.9077 | 0.4507 | 0.9612 | 0.0 | 0.0 | 0.0044 | 0.0 | nan | 0.4298 | 0.7138 | 0.0 | 0.0555 | 0.0004 | 0.0 | 0.0000 | 0.0002 | 0.0 | 0.4210 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.4768 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.6815 | 0.3562 | 0.5935 | 0.0 | 0.0 | 0.0043 | 0.0 |
127
+ | 2.6386 | 0.8 | 80 | 2.4834 | 0.1216 | 0.1831 | 0.6776 | nan | 0.8479 | 0.8715 | 0.0 | 0.0632 | 0.0005 | nan | 0.0 | 0.0000 | 0.0 | 0.8980 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.6096 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.9324 | 0.4880 | 0.9573 | 0.0 | 0.0 | 0.0088 | 0.0 | nan | 0.4463 | 0.7197 | 0.0 | 0.0604 | 0.0005 | 0.0 | 0.0 | 0.0000 | 0.0 | 0.5022 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.5004 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.6846 | 0.3790 | 0.5905 | 0.0 | 0.0 | 0.0086 | 0.0 |
128
+ | 2.4504 | 1.0 | 100 | 2.4704 | 0.1228 | 0.1842 | 0.6771 | nan | 0.8619 | 0.8589 | 0.0 | 0.0530 | 0.0006 | nan | 0.0 | 0.0 | 0.0 | 0.8886 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.6177 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.9365 | 0.5350 | 0.9510 | 0.0 | 0.0 | 0.0074 | 0.0 | nan | 0.4368 | 0.7208 | 0.0 | 0.0505 | 0.0005 | 0.0 | 0.0 | 0.0 | 0.0 | 0.5175 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.5053 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.6868 | 0.3948 | 0.6104 | 0.0 | 0.0 | 0.0073 | 0.0 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
129
 
130
 
131
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "heromiya/segformer-b0-finetuned-segments-sidewalk-2",
3
  "architectures": [
4
  "SegformerForSemanticSegmentation"
5
  ],
 
1
  {
2
+ "_name_or_path": "nvidia/segformer-b0-finetuned-ade-512-512",
3
  "architectures": [
4
  "SegformerForSemanticSegmentation"
5
  ],
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b622265a69c24451c434a8db131c4b20aa0dddecb43585ea3074af373d88c2e0
3
  size 14918708
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:261e8acce883aa34a32cd25a6421dfb2e0c8390cbc0b12b8bc203bdb3db2c1c4
3
  size 14918708
runs/Jan20_10-03-13_jupyter-admin01/events.out.tfevents.1737367409.jupyter-admin01.120.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:297401c6da5e5b25d71138b117c38e2a8ab2112f077c45ad2bf0baeca820b4f3
3
+ size 20694
runs/Jan20_10-08-48_jupyter-admin01/events.out.tfevents.1737367742.jupyter-admin01.120.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57e477f1e25465873ba4d3c270d2f9d7d66702961c29a1101ef47c10c22cefa3
3
+ size 53145
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24cbbafd102b25a34b7ef7d39beaf42e90a6883c253461e09baa6a3be5e7a1ec
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63b379aeccf65abf9b33d2f12a927a35ea21426a4c05b53e9708d71c56bff0ab
3
  size 5432